Plugins

Sidebar developer toolbox with 65 pure browser-side tools in 13 groups — JSON, code formatting, URL, encoding, hashing, encryption, text, and number/date utilities — with zero network requests. Registers as a tab in dsh-better-sidebar, which must be installed for the panel to appear.

Ecommerce research for DeepSeek Harness: OAuth into the Nexscope MCP server, marketplace data across Amazon, TikTok Shop, Walmart, Shopee, Temu and 1688, plus a bundled nexscope skill.

Wraps the separately installed agent-desktop CLI (`npm i -g agent-desktop`) as nine DSH tools (ad_status, ad_list_windows, ad_snapshot, ad_find, ad_click, ad_type, ad_press, ad_launch, ad_close_app) so an agent can list windows, read an accessibility tree, click a snapshot ref, type text, send keys, launch an app and close it gracefully. The plugin adds no automation logic of its own: it validates arguments, calls the CLI and returns the parsed JSON envelope, and asks the caller to take a fresh snapshot instead of retrying a stale ref, so a click never lands on a shifted target.

arXiv paper survey assistant with a settings-page UI, a local knowledge base, a feedback loop, keyword search plus optional local-embedding semantic search, and per-paper deep-read notes. Requires a configured DSH LLM provider; semantic search and full-text deep read need an optional Python environment (pymupdf + fastembed), otherwise they fall back to keyword search or are skipped.

Embeds a private local Sub2API gateway (Sub2API + PostgreSQL + Redis via Docker) into the DeepSeek Harness sidebar with automatic local login. Windows only, with Docker Desktop and its WSL2 backend already installed; the first start pulls about 250 MB of images and needs local ports 18080 and 18081 free.

Self-hosted SearXNG search provider: the bundled installer sets up and supervises a local instance on macOS/Linux/WSL (needs git and Python 3.11+), key-less and tracking-free; it probes the engines your network can reach and applies the recommended set in one click.

Mirrors an Android phone screen to a Windows PC over USB or Wi-Fi with scrcpy, and exposes start, stop, status, connect (reconnect after a phone reboot) and screenshot as an agent tool and a /mirror command. Requires scrcpy and adb installed on the host (winget install Genymobile.scrcpy); the plugin does not bundle them.

Per-session fast-delivery mode from the composer. New conversations start enabled; switching is refused while that conversation is running, and a read-only session-header badge shows on/off during a run. One switch drives three subsystems: a circuit breaker that short-circuits test and build commands instead of running them, an apply_patch tool that writes SEARCH/REPLACE hunks atomically (all anchors must match or nothing is written), and a dehydrator that trims terminal output to a pass line or the last 15 error lines.

Persistent Codex advisor threads for DSH sessions, with six native tools, a Codex trail, a sidebar status card, and explicit model/effort provenance. Requires a locally installed Codex CLI with app-server support and a logged-in ChatGPT/Codex account (the CLI is not bundled); tested on Windows 11 with DSH Desktop 0.2.1-rc.5.

Cross-session long-term memory for DSH: eight memory layers, four notebooks, hybrid SQLite FTS5/vector/graph retrieval, agent-driven automatic capture, write lifecycle hooks, optional write audit, project spaces, forgetting and a visual management page. Full FTS5/vector/graph retrieval needs the bundled Go service, which ships only as a Windows x64 prebuilt; on macOS/Linux, build it from source or the plugin falls back to Node SQLite without FTS5 and retrieval degrades.

Bridges the shared ~/.agentloom store between DeepSeek Harness and Codex: injects the shared memories and the AGENTS.md entries the context budget truncates into the system prompt, and adds six loom_* tools for status, sync, memory search/list/add and skill listing. Requires the agentloom CLI installed and a one-time agentloom init; the seven-tool MCP bridge in the same repo is a separate package for MCP clients.

A cross-workspace Library for DeepSeek Harness: agents record files, tools, environments, knowledge and work records so any later session can index, search and reuse them.

Adds a knowledge-base sidebar backed by the separately installed local Obsidian Quote service: select registered vaults or folders, retrieve read-only note excerpts and cited context, extract rules, generate project convention briefs, and view shared citation statistics.

Zhinao (second brain) for DeepSeek Harness: Markdown-authoritative layered memory (L1 long-term model gated by user confirmation / L2 knowledge with mandatory sources / L3 recent status under daily quotas), a local recall ledger explaining every injection, lifecycle engine with weekly review and a Web panel. First-run wizard initializes a blank brain, adopts an existing Zhinao directory read-only, or fills in only missing skeleton files; existing files are never touched.

Cross-session memory for DeepSeek Harness: extracts durable facts from sessions in the background, recalls relevant memories on demand, and keeps a layered summary, a persona snapshot and a commitment ledger; data stays local unless you point it at your own private Git repository.

Elysia's memory plugin for dsh. One shared, human-editable MEMORY.md across every session: two-disk mirror, history snapshots, cross-process write lock; entries tier between the main file and a searchable archive by hit frequency; retrieval is keyword co-occurrence plus BM25. Nine sections (persona, requirements, corrections, lessons, methods, requests, sessions, method library, ingested docs) plus a dedicated self-identity section for a character's own self-cognition, injected above the persona. Ships an opt-in memory pack (packs/elysia: 61,903-char identity + 2,482-char persona, distilled from 1,696 officially-confirmed voice lines and 112,175 dialogue lines — not written by hand, measured) that is off by default, backs up before writing, only touches identity/persona, and can be uninstalled. Also opt-in voice playback through a local GPT-SoVITS engine, a skills library, and a sticker library that sends a fitting sticker at the right moment.

Layered context management: at each turn end older tool output becomes a deterministic card, the model can fold older ranges into its own summaries in up to three tiers (compress), and every original is archived locally for decompress and search_context. Works alongside DSH-Mem0: superseded runtime-context snapshots (such as recalled memories) are never archived, carded or folded, and are replaced by a one-line placeholder at turn end when the prompt cache is already broken, when the saving outweighs the cache miss, or above 75% of the window; a strataBudget service (pressure, allowance, countTokens) and a strata/fold-landed event are provided for other context plugins; strata_status warns when DSH's automatic compaction is off or its official summary keeps failing. Its L1 layer, archive rotation, prune guard and preset takeover are forked from dsh-live-compact 1.0.6 (MIT); uninstall dsh-live-compact or billion-context first — they replace the same compaction rows and Strata will not take over while either is installed.

Multi-character companions with optional personas, editable per-character memories, persistent chat bindings, and QQ and WeChat bot connections with QR login and refresh. QQ requires a separately installed local NapCat instance; WeChat uses the official ClawBot/iLink channel.

QQ (OneBot 11 / NapCat) channel for DeepSeek Harness: bridges QQ private chats and group chats into their own dsh sessions. Ships group guardrails (mention-only, quiet hours, cooldowns, daily quota, peak-hour mute), a tool gate with write-action audit, an outbound filter that stops the model from echoing input tags, voice transcription, media and forwarded-card support, dryRun and usage stats. Forked from dsh-onebot-qq 0.9.4. Cannot be installed alongside the upstream dsh-onebot-qq (two QQ channels on one NapCat crash-loop DSH). Private chats answer admins only (an empty admin list means nobody); group chats default to all groups and answer any @-mention, so set groupPolicy to allowlist to restrict who can drive the agent.

Merges your configured, runtime-registered and locally cached models into one panel, probes and minimal-request tests them, pulls each channel's upstream /v1/models catalog, and chains the keepers into named schemes. A virtual ModelPool provider fails over at request time with per-model cooldowns, exponential backoff, image-request avoidance for text-only models, and a 10-minute memory for rejected reasoning levels. Adds a token ledger by day and model with CSV export, and 21 regression probes. Not a fork of dsh-llm-fallbacks.

Claude-style palette and typography for the DSH Web GUI — paper-white surface, near-black ink and terracotta accent derived from the Codex absolutely theme, warm neutral and accent ramps bound to 82 native token overrides for both light and dark, Anthropic Sans/Serif/Mono typography, and interface chrome sized with the content font setting. The fonts are not bundled — install them separately, otherwise the UI falls back to system fonts.

Shows account balance, current peak/off-peak token price and today's spend in the dsh sidebar; today's spend is read from the local dsh-cost-meter ledger (~/.dsh/.dshw-usage.json), so it shows a dash until dsh-cost-meter is installed.

Exact per-session spend for DeepSeek Harness, billed request by request at the peak or off-peak rate in force when that request was sent.

One click beside the composer turns a half-formed draft into a structured prompt the AI can act on: goal, constraints, output format and acceptance criteria filled in, placeholders only where a real decision is missing. Rewritten in place and never sent — undo with one click or Ctrl+Z. Four editable presets (general / code / writing / translation), optional conversation context to resolve references, and a model that either follows the session or is pinned to a chosen provider and reasoning effort. Requests survive session switches and typing while a rewrite is in flight; a result that no longer matches the draft is kept for retry instead of overwriting it. Pure JS, no build, no bundled dependencies.